research-paper-downloader

Download academic papers from open-access sources when the user provides a DOI/arXiv ID or requests a keyword-based paper search, and return the saved PDF path.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/research-paper-downloader/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill-specific halves (usage examples, source fallback, file rules) are actionable and concrete, but the body is padded with generic boilerplate sections, lacks an explicit validation checkpoint for batch keyword downloads, and fails to link the bundled references/apis.md. Tightening and re-organizing would lift the score meaningfully.

Suggestions

Remove or collapse the generic boilerplate sections (When Not to Use, Required Inputs, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling) into a few skill-specific lines; their content is largely process guidance Claude already applies.

Add an explicit post-download validation step for the batch keyword-search path (e.g. verify each PDF is non-empty and well-formed before reporting the path), so workflow clarity is not capped at 3 for batch operations.

Link references/apis.md from the Implementation Details section instead of inlining the API/source list, and align the 'Quick Validation' expected output with the skill's actual PDF-path return contract.

Dimension	Reasoning	Score
Conciseness	Roughly the second half of the body ('When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation') is generic process boilerplate that restates knowledge Claude already has rather than skill-specific guidance, and the 'Quick Validation' expected output is inconsistent with the skill (a PDF path, not 'research_paper_downloader_result.md'). This is noticeably verbose with several padded sections, matching anchor 2 rather than 3.	2 / 5
Actionability	Provides concrete, copy-pasteable CLI commands ('python scripts/download.py --doi ...', '--arxiv', '--search --max-results') plus a runnable Python example and documented config keys. Not a 5 because the Python import ('from download import ...') is hedged as 'expected to be provided' and may not match the actual module surface of scripts/download.py.	4 / 5
Workflow Clarity	A sequence exists (numbered source fallback order, error-handling expectations), but checkpoints are implicit and the recommended workflow is generic boilerplate. Because keyword search downloads multiple PDFs (a batch operation) with no explicit post-download validation step, workflow clarity is capped at 3 per the batch-operations guideline.	3 / 5
Progressive Disclosure	The body has reasonable section headers but inlines the API/source details that already exist as a separate bundle file (references/apis.md), and that file is never referenced or signaled from the body — a clear organization gap. This matches anchor 3 (some structure, references not clearly signaled, content that should be separate is inline).	3 / 5
	Total	12 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed: third-person voice, explicit what-and-when structure, concrete actions, and distinct triggers tied to DOI/arXiv/keyword inputs. Minor gains are possible by adding a few natural synonyms and hinting at multi-source fallback.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Download academic papers from open-access sources', 'keyword-based paper search', and 'return the saved PDF path' — across DOI/arXiv/search input modes, with only minor gaps in coverage. Not a 5 because it does not comprehensively enumerate all retrieval behaviors (e.g. multi-source fallback) the body later details.	4 / 5
Completeness	Explicitly answers both what ('Download academic papers from open-access sources ... and return the saved PDF path') and when ('when the user provides a DOI/arXiv ID or requests a keyword-based paper search') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say — 'DOI', 'arXiv ID', 'keyword-based paper search', 'academic papers', 'open-access', 'PDF path' — giving good coverage. Not a 5 because common synonyms like 'preprint', 'research paper', or 'scholarly article' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — open-access academic paper retrieval keyed on DOI/arXiv/keyword — with distinct triggers and minimal overlap risk against unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/research-paper-downloader/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.